Ornith-1.5-397B needs about 245.8 GB of memory at Q4_K_M (a 244.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 244.3 GB (Q4_K_M) to 428.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.1 GB.
397B mixture‑of‑experts model with vision and large context
Ornith‑1.5‑397B is a 397 billion‑parameter mixture‑of‑experts model built on the qwen35moe architecture. It supports vision tasks and was trained on a 262,144‑token context window. The model is released under the MIT license.
Good at
- Vision‑enabled reasoning
- Large‑context text generation
- Mixture‑of‑experts scaling
Limits
- Requires 8 k context for estimates
- Large VRAM needed for full model
- No explicit language support list
Best for
- Complex multimodal queries
- Long‑form document analysis
- Research prototyping
Who it’s for. Engineers and researchers needing a high‑capacity, vision‑capable model for experimentation. The MIT license allows free use and modification.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 244.3 GB | 245.8 GB | Too big | Get file → | |
| Q5_K_M | 286.3 GB | 287.8 GB | Too big | Get file → | |
| Q6_K | 331.0 GB | 332.5 GB | Too big | Get file → | |
| Q8_0 | 428.5 GB | 430.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (244 GB file, ~246 GB memory). For 16 GB VRAM, Q5_K_M (286 GB file, ~288 GB memory). For 32 GB VRAM, Q6_K (331 GB file, ~333 GB memory). For 64 GB VRAM, Q8_0 (429 GB file, ~430 GB memory). Memory estimates are approximate.
What GPU do you need for Ornith-1.5-397B?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Ornith-1.5-397B quant should you choose?
Q4_K_M is the usual starting point for Ornith-1.5-397B: it balances file size and quality well. Here it is a 244.3 GB file.
The Q8_0 file is 428.5 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ornith-1.5-397B
How much VRAM does Ornith-1.5-397B need?
About 245.8 GB at Q4_K_M with an 8K context window. That is the 244.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Ornith-1.5-397B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 245.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ornith-1.5-397B GGUF?
It depends on the quant: Q4_K_M is 244.3 GB, Q5_K_M is 286.3 GB, Q6_K is 331.0 GB, Q8_0 is 428.5 GB.
What context length does Ornith-1.5-397B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.0 GB at 8K and 4.1 GB at 32K.
Where can I download Ornith-1.5-397B GGUF?
The files are on Hugging Face in the ornith-ai/Ornith-1.5-397B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Ornith-1.5-397B use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Ornith‑1.5‑397B on 8 GB VRAM?
No, the smallest quant requires ~246 GB VRAM. You would need at least 256 GB VRAM to run the model.
Does the model support vision tasks?
Yes, the model has detected vision abilities and can process image inputs.
What license does the model use?
The model is released under the MIT license, allowing free use and modification.